Researcher - AI-based Weather Prediction for Yr

Tor Skaslien; Oslo; On-site; NOK 580,000 - 800,000; Full time

Benefits offered by this job

Flexible hours

Language training

Annual training time

Job summary

MET Norway seeks a highly skilled researcher to develop and operationalise machine-learning based weather prediction, translating advances in ML into improved forecasts and services. The role focuses on Bris, a large-scale ML model running operationally at MET Norway, with a global grid and high-resolution areas.

You will build forecast products, contribute to open-source software like the Anemoi framework, collaborate with users and international partners, and participate in research projects

Qualifications

• PhD in meteorology, geophysics, statistics, computer science, physics, applied mathematics, or equivalent.

Responsibilities

• Research, development, validation and operationalisation of Bris.
• Development of forecast products for internal and external users, including services such as Yr and Værio.
• Develop the operational systems that deliver real-time data to Yr and to our API.
• Evaluate and validate forecast performance using independent observational datasets and verification methods.
• Contribute to open-source software development.
• Engagement with stakeholders and users.
• Participate in national and international research projects, including proposal writing and scientific publications.

Skills

PhD in meteorology

ML for weather

Graph neural nets

Transformers

DL frameworks

Python

Forecast verification

Collab/communication

Education

PhD in meteorology or related field

Tools

PyTorch

TensorFlow

JAX

Python data tooling

Job description

About the position

The successful candidate will play an important role in developing and operationalising machine-learning-based weather prediction and translating advances in ML into improved weather forecasts and services.

This work involves research, development, validation and operationalisation ofBris, a large-scale ML-based weather prediction model running operationally at MET Norway. Bris is a global model with a flexible stretched grid, allowing high resolution to be concentrated over areas of particular interest while retaining lower resolution elsewhere. The work includes developing and testing new approaches to improve predictive accuracy across a wide range of Nordic and Arctic weather conditions, optimizing training and inference pipelines, and expanding the model's usability for different applications and users.

An important part of the position is to bring data-driven forecasts from research into operational weather services. This includes developing forecast products for internal and external users, contributing to the operational systems that deliver real-time forecast data to services such as Yr and the MET Norway API, and evaluating forecast performance using independent observations and appropriate verification methods. The position also involves contributing to open-source software development, including the Anemoi framework, which is developed in collaboration with many European meteorological services.

The successful candidate will work closely with users and stakeholders to understand requirements and translate them into useful forecast products and services. The position also provides opportunities to participate in national and international research projects, including scientific publications and proposal development.

The position offers an opportunity to work at the forefront of rapidly developing AI methods for weather prediction, combining machine learning, atmospheric science, observations and high-performance computing. The results will contribute to the integration of data-driven prediction models into the weather forecasting value chain and ultimately support improved weather services for the general public and professional users.

The position is based in Oslo. The working language at MET Norway is Norwegian. Fluency in written and spoken English is required. Applicants who do not speak Norwegian are expected to be willing to learn Norwegian; language training will be provided.

The position's responsibilities and work areas

• Research, development, validation and operationalisation of Bris.
• Development of forecast products for internal and external users, including services such as Yr and Værio.
• Develop the operational systems that deliver real-time data to Yr and to our API.
• Evaluate and validate forecast performance using independent observational datasets and verification methods.
• Contribute to open-source software development.
• Engagement with stakeholders and users.
• Participate in national and international research projects, including proposal writing and scientific publications.

Required skills and qualifications

• PhD in meteorology, geophysics, statistics, computer science, physics, applied mathematics, or equivalent.
• Strong machine learning skills, including experience with graph neural networks, transformers, or diffusion models, and proficiency in at least one framework (PyTorch, TensorFlow, JAX).
• Experience in software development, collaborative coding, and building ML-ready datasets (Python or similar).
• Knowledge of forecast verification and model evaluation methods.
• Excellent analytical, collaborative, and communication skills, with the ability to work independently in interdisciplinary teams.

Conditions

• Good working environment and professional challenges in a modern, technological environment.
• Membership in the Statens Pensjonskasse (SPK) with good schemes for pensions, insurances and mortgages (read more here: https://www.spk.no/Medlemskap-i-SPK/)
• Flexible working hours with summer time
• Possibility of one hour of training during working hours per week
• Salary on the governmental salary scales dependent on qualifications and experience, NOK 580,000 - 800,000 pr. year. A 2% statutory contribution to the Statens Pensjonskasse is deducted from the salary.
• The first 6 months is a mutual trial period.

Diversity and positive discrimination

We believe that diversity is a strength, and want employees with different skills, subject combinations, work experience, gender, life experience and perspectives.We encourage all qualified candidates to apply for a job with us regardless of ethnic background, age or ability.

We practice positive discrimination, and will call at least one qualified applicant in each of these groups for an interview: applicants with a disability, immigrant background or gaps in the CV.To be considered in one or more of these categories, you mustmark the appropriate category in your application.

Functional impairment:applicants who need accommodation in the workplace or in the working relationship.

Immigrant background: applicants who have themselves immigrated to Norway. Or who was born in Norway with two parents who both immigrated to Norway.

Gaps in CV: applicants who have had a break from work, education or training for a total of at least two years in the last five years due to e.g. physical or mental illness or injury, intoxication or punishment.

The ticks can be used for anonymised statistics or reporting purposes.

Publication of applicant listsfor public sector positions is an important principle to ensure transparency. If you want your name to be excluded from the applicant list, you must ask for it yourself, and give us a reason. In order to be exempted from the public applicant list, your justification for exemption must outweigh the consideration of transparency in the applicant list. If your request is not accepted, you will have the opportunity to withdraw your application.